split.c

   1 /*
   2  * wiggle - apply rejected patches
   3  *
   4  * Copyright (C) 2003 Neil Brown <neilb@cse.unsw.edu.au>
   5  *
   6  *
   7  *    This program is free software; you can redistribute it and/or modify
   8  *    it under the terms of the GNU General Public License as published by
   9  *    the Free Software Foundation; either version 2 of the License, or
  10  *    (at your option) any later version.
  11  *
  12  *    This program is distributed in the hope that it will be useful,
  13  *    but WITHOUT ANY WARRANTY; without even the implied warranty of
  14  *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15  *    GNU General Public License for more details.
  16  *
  17  *    You should have received a copy of the GNU General Public License
  18  *    along with this program; if not, write to the Free Software Foundation, Inc.,
  19  *    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  20  *
  21  *    Author: Neil Brown
  22  *    Email: <neilb@suse.de>
  23  */
  24
  25 /*
  26  * Split a stream into words or lines
  27  *
  28  * A word is one of:
  29  *    string of [A-Za-z0-9_]
  30  *    or string of [ \t]
  31  *    or single char (i.e. punctuation and newlines).
  32  *
  33  * A line is any string that ends with \n
  34  *
  35  * As a special case to allow proper aligning of multiple chunks
  36  * in a patch, a word starting \0 will include 20+ chars with a newline
  37  * second from the end.
  38  *
  39  * We make two passes through the stream.
  40  * Firstly we count the number of item so an array can be allocated,
  41  * then we store start and length of each item in the array
  42  *
  43  */
  44
  45 #include        "wiggle.h"
  46 #include        <stdlib.h>
  47 #include        <ctype.h>
  48 #include        <stdlib.h>
  49
  50 #include "ccan/hash/hash.h"
  51
  52 static int split_internal(char *start, char *end, int type,
  53                           struct elmnt *list)
  54 {
  55         int cnt = 0;
  56
  57         while (start < end) {
  58                 char *cp = start;
  59                 char *cp2;
  60                 int prefix = 0;
  61
  62                 if (type == (ByWord | IgnoreBlanks))
  63                         while (cp < end &&
  64                                (*cp == ' ' || *cp == '\t')) {
  65                                 prefix++;
  66                                 cp++;
  67                         }
  68                 start = cp;
  69
  70                 if (*cp == '\0' && cp+19 < end) {
  71                         /* special word */
  72                         cp += 19;
  73                         cp += strlen(cp) + 1;
  74                 } else
  75                         switch (type & ByMask) {
  76                         case ByLine:
  77                                 while (cp < end && *cp != '\n')
  78                                         cp++;
  79                                 if (cp < end)
  80                                         cp++;
  81                                 break;
  82                         case ByWord:
  83                                 if (isalnum(*cp) || *cp == '_') {
  84                                         do
  85                                                 cp++;
  86                                         while (cp < end
  87                                                && (isalnum(*cp)
  88                                                    || *cp == '_'));
  89                                 } else if (*cp == ' ' || *cp == '\t') {
  90                                         do
  91                                                 cp++;
  92                                         while (cp < end
  93                                                && (*cp == ' '
  94                                                    || *cp == '\t'));
  95                                 } else
  96                                         cp++;
  97                                 break;
  98                         }
  99                 cp2 = cp;
 100                 if (type == (ByWord | IgnoreBlanks) &&
 101                     *start && *start != '\n')
 102                         while (cp2 < end &&
 103                                (*cp2 == ' ' || *cp2 == '\t' || *cp2 == '\n')) {
 104                                 cp2++;
 105                                 if (cp2[-1] == '\n')
 106                                         break;
 107                         }
 108                 if (list) {
 109                         list->start = start;
 110                         list->len = cp-start;
 111                         list->plen = cp2-start;
 112                         list->prefix = prefix;
 113                         if (*start)
 114                                 list->hash = hash(start, list->len, 0);
 115                         else
 116                                 list->hash = atoi(start+1);
 117                         list++;
 118                 }
 119                 cnt++;
 120                 start = cp2;
 121         }
 122         return cnt;
 123 }
 124
 125 struct file split_stream(struct stream s, int type)
 126 {
 127         int cnt;
 128         struct file f;
 129
 130         char *c, *end;
 131
 132         end = s.body+s.len;
 133         c = s.body;
 134
 135         cnt = split_internal(c, end, type, NULL);
 136         f.list = xmalloc(cnt*sizeof(struct elmnt));
 137
 138         f.elcnt = split_internal(c, end, type, f.list);
 139         return f;
 140 }